CN117520864B - Multi-feature fusion intelligent matching method for data elements - Google Patents
Multi-feature fusion intelligent matching method for data elements Download PDFInfo
- Publication number
- CN117520864B CN117520864B CN202410023026.1A CN202410023026A CN117520864B CN 117520864 B CN117520864 B CN 117520864B CN 202410023026 A CN202410023026 A CN 202410023026A CN 117520864 B CN117520864 B CN 117520864B
- Authority
- CN
- China
- Prior art keywords
- data
- product
- user
- products
- feature
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 18
- 230000004927 fusion Effects 0.000 title claims abstract description 14
- 239000013598 vector Substances 0.000 claims abstract description 37
- 230000036962 time dependent Effects 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 description 9
- 238000005457 optimization Methods 0.000 description 2
- 238000013480 data collection Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a multi-feature fusion intelligent matching method of data elements, which belongs to the field of data product retrieval, and comprises the steps of respectively endowing weight coefficients to the data element features of all data products to obtain the data element feature weight coefficients of all the data products; respectively normalizing the data element characteristic weighting coefficients of each data product to obtain characteristic vectors of the data element characteristic weighting scoring values of each data product; acquiring historical transactions of a user, and acquiring feature preference feature vectors of element features of user data according to the historical transactions of the user; calculating the matching degree of each data product and the user retrieval requirement according to the feature vector of the data element feature weighted scoring value of each data product and the user element feature preference feature vector; and according to the matching degree of each data product and the search requirement of the user, taking the data product with the highest matching degree as the optimal search result, and completing matching. The invention solves the problem of asymmetric information in the process of retrieving the data product.
Description
Technical Field
The invention belongs to the field of data product retrieval, and particularly relates to a multi-feature fusion intelligent matching method for data elements.
Background
On a data transaction platform, characteristics of a data product include not only price, but also timeliness, quality and other factors. On-line commodity supply and demand relation matching is one of the key problems of an electronic commerce platform. There are Search Engine Optimization (SEO), real-time inventory management, demand prediction, supply chain optimization, etc. And providing supply and demand matching for the online transaction service of the traditional commodity. The novel online data transaction has the characteristics that the online data transaction is very different from online data commodity transaction, and the online data transaction has the characteristics of digitality, diversity, real-time performance, privacy and the like, and plays an increasingly important role in modern commerce. However, the risks and compliance issues associated therewith also need to be carefully treated.
Disclosure of Invention
Aiming at the defects in the prior art, the intelligent matching method for multi-feature fusion of the data elements solves the problem of information asymmetry in the process of data product retrieval.
In order to achieve the aim of the invention, the invention adopts the following technical scheme: a multi-feature fusion intelligent matching method for data elements comprises the following steps:
s1, respectively giving weight coefficients to the data element characteristics of each data product to obtain the data element characteristic weight coefficients of each data product;
s2, respectively normalizing the data element characteristic weighting coefficients of each data product to obtain characteristic vectors of data element characteristic weighting scoring values of each data product;
s3, acquiring historical transactions of the user, and obtaining feature vectors of feature preferences of the user data elements according to the historical transactions of the user;
s4, calculating the matching degree of each data product and the user retrieval requirement according to the feature vector of the data element feature weighted scoring value of each data product and the user element feature preference feature vector;
and S5, according to the matching degree of each data product and the search requirement of the user, taking the data product with the highest matching degree as the optimal search result, and completing matching.
The beneficial effects of the invention are as follows: by considering the weighted matching of the data element characteristics of the data product and the user element characteristics, the user retrieval efficiency can be improved, the data product which is more effective and meets the real-time requirement can be provided, and the creation of a more efficient and transparent data transaction ecosystem is facilitated.
Further, the data element features of each data product in the step S1 include data cost value, data timeliness and data scarcity; the data element characteristic weighting coefficients of each of the data products include a data cost value weighting coefficient, a data timeliness weighting coefficient, and a data scarcity weighting coefficient.
The beneficial effects of the above-mentioned further scheme are: the data is subjected to feature extraction according to the three aspects of cost, timeliness and scarcity, so that the features of the data product can be effectively quantized, and the matching difficulty is reduced.
Further, the expression of the data cost value weighting coefficient is:
wherein,weighting coefficients for cost value of data; />Is->The cost value of the data product; />Numbering the data products; />A total number of data products; />To generate +.>The number of people required to access the data product; />To generate +.>The time required for the data product.
The beneficial effects of the above-mentioned further scheme are: and the cost value of the data product is effectively quantified, and the matching difficulty is reduced.
Further, the expression of the time-efficiency weighting coefficient of the data is:
wherein,a time-lapse weighting coefficient for the data; />Is->The timeliness value of the data product; />Numbering the data products; />A total number of data products; />Is->The data time involved in the data product; />Is the current time.
The beneficial effects of the above-mentioned further scheme are: and the timeliness of the data product is effectively quantified, and the matching difficulty is reduced.
Further, the expression of the data scarcity weighting coefficient is:
wherein,weighting coefficients for data scarcity; />Is->The scarcity value of the data product; />Numbering the data products; />A total number of data products; />Is->Data amount of the data product; />Is->The total amount of data of the category to which the data product belongs.
The beneficial effects of the above-mentioned further scheme are: and the scarcity of the data product is effectively quantified, and the matching difficulty is reduced.
Further, the feature vector of the data element feature weighted score value of each data product in step S2 is:
wherein,is->A feature vector of data element feature weighted scoring values for the data product; />Numbering the data products; />Is->A normalized value of the data cost value for the data product; />Is->A time-dependent normalized value of the data product; />Is->Normalized values of data scarcity for the data product; />Is->A data cost value weighting coefficient for the data product; />Is->A data timeliness weighting coefficient for the data product; />Is->Data sparsity weighting coefficients for the data products; />Is->The data cost value of the data product; />The minimum value of the cost value of the data in all data products; />Maximum value of data cost value for all data products; />Is the firstData timeliness of the data product; />The minimum value of the timeliness of the data in all data products; />Maximum value of timeliness of data in all data products; />Is->Data scarcity of data products; />Is the minimum value of data scarcity in all data products; />Maximum value of data scarcity for all data products; />Is a multiplication symbol.
The beneficial effects of the above-mentioned further scheme are: and comprehensively considering the cost value, timeliness and scarcity of the data products, and integrally quantifying the data products to reduce the matching difficulty.
Further, the user data element feature preference feature vector in step S3 is:
wherein,preference feature vectors for user data element features; />An average value of data cost value for data products historically purchased by the user; />An average value of data timeliness for data products historically purchased by the user; />An average value of data scarcity for data products historically purchased by the user; />+.>The data cost value of the data product; />Numbering data products historically purchased for a user; />+.>Data timeliness of the data product; />+.>Data scarcity of data products.
The beneficial effects of the above-mentioned further scheme are: and quantifying the characteristic preference of the user data element according to the user history behavior, and reducing the matching difficulty.
Further, the matching degree between each data product and the user retrieval requirement is as follows:
wherein,is->Matching degree of the data product and the user retrieval requirement; />Numbering the data products; />Is->A feature vector of data element feature weighted scoring values for the data product; />Preference feature vectors for user data element features; />Is the L2 norm; />Is a multiplication symbol.
The beneficial effects of the above-mentioned further scheme are: and calculating the matching degree of the data product and the user retrieval requirement according to the feature vector of the data element feature weighted scoring value of the data product and the user data element feature preference feature vector, converting massive data and user loving into lighter weight and more specific vectors for calculation, reducing the matching difficulty and providing guidance for recommending the data product.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
The following description of the embodiments of the present invention is provided to facilitate understanding of the present invention by those skilled in the art, but it should be understood that the present invention is not limited to the scope of the embodiments, and all the inventions which make use of the inventive concept are protected by the spirit and scope of the present invention as defined and defined in the appended claims to those skilled in the art.
As shown in fig. 1, in one embodiment of the present invention, a data element multi-feature fusion intelligent matching method includes the following steps:
s1, respectively giving weight coefficients to the data element characteristics of each data product to obtain the data element characteristic weight coefficients of each data product;
s2, respectively normalizing the data element characteristic weighting coefficients of each data product to obtain characteristic vectors of data element characteristic weighting scoring values of each data product;
s3, acquiring historical transactions of the user, and obtaining feature vectors of feature preferences of the user data elements according to the historical transactions of the user;
s4, calculating the matching degree of each data product and the user retrieval requirement according to the feature vector of the data element feature weighted scoring value of each data product and the user element feature preference feature vector;
and S5, according to the matching degree of each data product and the search requirement of the user, taking the data product with the highest matching degree as the optimal search result, and completing matching.
The data element characteristics of each data product in the step S1 comprise data cost value, data timeliness and data scarcity; the data element characteristic weighting coefficients of each of the data products include a data cost value weighting coefficient, a data timeliness weighting coefficient, and a data scarcity weighting coefficient.
In this embodiment, the data cost value reflects the labor cost and time cost incurred in the process of data generation. The cost value of the data is reflected according to the duration of the data collection. The longer the time spent, the greater the cost value. The data timeliness value score reflects the information timeliness or real-time of the data. The closer the data time distance is now, the greater the timeliness value.
The expression of the data cost value weighting coefficient is as follows:
wherein,weighting coefficients for cost value of data; />Is->The cost value of the data product; />Numbering the data products; />A total number of data products; />To generate +.>The number of people required to access the data product; />To generate +.>The time required for the data product.
The expression of the time-efficiency weighting coefficient of the data is as follows:
wherein,a time-lapse weighting coefficient for the data; />Is->The timeliness value of the data product; />Numbering the data products; />A total number of data products; />Is->The data time involved in the data product; />Is the current time.
The expression of the data scarcity weighting coefficient is as follows:
wherein,weighting coefficients for data scarcity; />Is->The scarcity value of the data product; />Numbering the data products; />A total number of data products; />Is->Data amount of the data product; />Is->The total amount of data of the category to which the data product belongs.
The feature vector of the data element feature weighted score value of each data product in the step S2 is:
wherein,is->A feature vector of data element feature weighted scoring values for the data product; />Numbering the data products; />Is->A normalized value of the data cost value for the data product; />Is->A time-dependent normalized value of the data product; />Is->Normalized values of data scarcity for the data product; />Is->A data cost value weighting coefficient for the data product; />Is->A data timeliness weighting coefficient for the data product; />Is->Data sparsity weighting coefficients for the data products; />Is->The data cost value of the data product; />The minimum value of the cost value of the data in all data products; />Maximum value of data cost value for all data products; />Is the firstData timeliness of the data product; />The minimum value of the timeliness of the data in all data products; />Maximum value of timeliness of data in all data products; />Is->Data scarcity of data products; />Is the minimum value of data scarcity in all data products; />Maximum value of data scarcity for all data products; />Is a multiplication symbol.
The user data element feature preference feature vector in the step S3 is:
wherein,preference feature vectors for user data element features; />An average value of data cost value for data products historically purchased by the user; />An average value of data timeliness for data products historically purchased by the user; />An average value of data scarcity for data products historically purchased by the user; />+.>The data cost value of the data product; />Numbering data products historically purchased for a user; />+.>Data timeliness of the data product; />+.>Data scarcity of data products.
In this embodiment, a data product suitable for the user's requirement is provided to the user through the user's historical purchasing behavior, and when the number of times of purchase of the user is greater than or equal to 1, the user starts to record the characteristic preference of the data element of the data product. And sorting the average value of the characteristic coefficients of each data element characteristic of each data product purchased by the user, obtaining the preference of the user on the data element characteristic, and weighting the matching of the user demands through the average value of the characteristic coefficients.
The matching degree of each data product and the search requirement of the user is as follows:
wherein,is->Matching degree of the data product and the user retrieval requirement; />Numbering the data products; />Is->A feature vector of data element feature weighted scoring values for the data product; />Preference feature vectors for user data element features; />Is the L2 norm; />Is a multiplication symbol.
The beneficial effects of the invention are as follows: the user can obtain the data product which is matched with the user best according to the unique requirement and budget, thereby providing more personalized experience; the user can select more economical and practical data products according to budget allocation and data cost scoring, so that the data purchasing cost is reduced; the user can select the data product which meets the real-time requirement according to the requirement of the user on the timeliness of the data, so that timely information is ensured to be obtained; the suppliers can better know the demands of users, provide more attractive data products, reduce the waste of resources and improve the efficiency and satisfaction of transactions; the data provider can optimize the data product according to the requirements and scores of the users, so that the data product meets the market requirements, and the value and sales of the data product are improved; the weighted matching reduces the information asymmetry between the user and the provider, so that the two parties can more easily understand the requirements and the provision of the other party, and the potential communication problem is reduced; through weighted matching, the characteristics (such as cost and timeliness value) of the data products are more definite, users and suppliers can more easily compare different products, and the market transparency is improved; the user is able to acquire data products that better meet their needs and expectations, and thus more satisfied with the purchased data, enhancing the user's loyalty to the platform or vendor. By weighting and matching the supply and demand of data transaction, more effective, economical and practical data products meeting the real-time requirements can be provided, meanwhile, the transparency of the market and the satisfaction of users are enhanced, and the creation of a more efficient and transparent data transaction ecosystem is facilitated.
Claims (7)
1. The intelligent matching method for multi-feature fusion of the data elements is characterized by comprising the following steps of:
s1, respectively giving weight coefficients to the data element characteristics of each data product to obtain the data element characteristic weight coefficients of each data product; the data element characteristics of each data product in the step S1 comprise data cost value, data timeliness and data scarcity; the data element characteristic weighting coefficients of each data product comprise a data cost value weighting coefficient, a data timeliness weighting coefficient and a data scarcity weighting coefficient;
s2, respectively normalizing the data element characteristic weighting coefficients of each data product to obtain characteristic vectors of data element characteristic weighting scoring values of each data product;
s3, acquiring historical transactions of the user, and obtaining feature vectors of feature preferences of the user data elements according to the historical transactions of the user;
s4, calculating the matching degree of each data product and the user retrieval requirement according to the feature vector of the data element feature weighted scoring value of each data product and the user element feature preference feature vector;
and S5, according to the matching degree of each data product and the search requirement of the user, taking the data product with the highest matching degree as the optimal search result, and completing matching.
2. The data element multi-feature fusion intelligent matching method according to claim 1, wherein the expression of the data cost value weighting coefficient is:
wherein,weighting coefficients for cost value of data; />Is->The cost value of the data product; />Numbering the data products; />A total number of data products; />To generate +.>The number of people required to access the data product; />To generate +.>The time required for the data product.
3. The intelligent matching method for multi-feature fusion of data elements according to claim 1, wherein the expression of the time-efficiency weighting coefficient of the data is:
wherein,a time-lapse weighting coefficient for the data; />Is->The timeliness value of the data product; />Numbering the data products; />A total number of data products; />Is->The data time involved in the data product; />Is the current time.
4. The data element multi-feature fusion intelligent matching method according to claim 1, wherein the expression of the data scarcity weighting coefficient is:
wherein,weighting coefficients for data scarcity; />Is->The scarcity value of the data product; />Numbering the data products; />A total number of data products; />Is->Data amount of the data product; />Is->The total amount of data of the category to which the data product belongs.
5. The intelligent matching method for multi-feature fusion of data elements according to claim 1, wherein the feature vector of the weighted score value of the feature of the data element in step S2 is:
wherein,is->A feature vector of data element feature weighted scoring values for the data product; />Numbering the data products;is->A normalized value of the data cost value for the data product; />Is->A time-dependent normalized value of the data product; />Is->Normalized values of data scarcity for the data product; />Is->A data cost value weighting coefficient for the data product; />Is->A data timeliness weighting coefficient for the data product; />Is->Data sparsity weighting coefficients for the data products; />Is->The data cost value of the data product; />The minimum value of the cost value of the data in all data products; />Maximum value of data cost value for all data products; />Is->Data timeliness of the data product; />The minimum value of the timeliness of the data in all data products; />Maximum value of timeliness of data in all data products; />Is->Data scarcity of data products; />Is the minimum value of data scarcity in all data products; />Maximum value of data scarcity for all data products; />Is a multiplication symbol.
6. The intelligent matching method for multi-feature fusion of data elements according to claim 1, wherein the user data element feature preference feature vector in step S3 is:
wherein,preference feature vectors for user data element features; />An average value of data cost value for data products historically purchased by the user; />An average value of data timeliness for data products historically purchased by the user; />An average value of data scarcity for data products historically purchased by the user; />+.>The data cost value of the data product; />Numbering data products historically purchased for a user; />+.>Data timeliness of the data product; />+.>Data scarcity of data products.
7. The intelligent matching method for multi-feature fusion of data elements according to claim 1, wherein the matching degree between each data product and the user search requirement is as follows:
wherein,is->Matching degree of the data product and the user retrieval requirement; />Numbering the data products;is->A feature vector of data element feature weighted scoring values for the data product; />Preference feature vectors for user data element features; />Is the L2 norm; />Is a multiplication symbol.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410023026.1A CN117520864B (en) | 2024-01-08 | 2024-01-08 | Multi-feature fusion intelligent matching method for data elements |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410023026.1A CN117520864B (en) | 2024-01-08 | 2024-01-08 | Multi-feature fusion intelligent matching method for data elements |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117520864A CN117520864A (en) | 2024-02-06 |
| CN117520864B true CN117520864B (en) | 2024-03-19 |
Family
ID=89766899
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410023026.1A Active CN117520864B (en) | 2024-01-08 | 2024-01-08 | Multi-feature fusion intelligent matching method for data elements |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117520864B (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012078768A (en) * | 2010-09-06 | 2012-04-19 | Nippon Telegr & Teleph Corp <Ntt> | Person matching device, method and program |
| CN109255651A (en) * | 2018-08-22 | 2019-01-22 | 重庆邮电大学 | A kind of search advertisements conversion intelligent Forecasting based on big data |
| CN112631560A (en) * | 2020-12-29 | 2021-04-09 | 上海海事大学 | Method and terminal for constructing objective function of recommendation model |
| CN113537728A (en) * | 2021-06-24 | 2021-10-22 | 上海阿法析地数据科技有限公司 | Intelligent recommendation system and recommendation method based on business recruitment in industrial park |
| CN115170247A (en) * | 2022-08-03 | 2022-10-11 | 杭州么贝软件科技有限公司 | Intelligent matching recommendation method for commodities of e-commerce shopping platform |
| CN115391669A (en) * | 2022-10-31 | 2022-11-25 | 江西渊薮信息科技有限公司 | Intelligent recommendation method and device and electronic equipment |
| CN115422452A (en) * | 2022-08-30 | 2022-12-02 | 温州佳润科技发展有限公司 | Smart home control method, device, equipment and storage medium based on big data |
| CN116402524A (en) * | 2023-02-22 | 2023-07-07 | 扬州市职业大学(扬州开放大学) | Video software user payment preference and influence factor analysis system thereof |
| CN116523597A (en) * | 2023-05-02 | 2023-08-01 | 肖刚 | E-commerce customization recommendation method for big data cloud entropy mining |
| CN116596564A (en) * | 2023-02-21 | 2023-08-15 | 重庆协洽科技有限公司 | Method based on customer preference product adaptation technology |
| CN116680320A (en) * | 2023-06-13 | 2023-09-01 | 张琼琼 | Mixed matching method based on big data |
| CN116739794A (en) * | 2023-08-10 | 2023-09-12 | 北京中关村银行股份有限公司 | User personalized scheme recommendation method and system based on big data and machine learning |
| CN117172725A (en) * | 2023-08-28 | 2023-12-05 | 合肥人工智能与大数据研究院有限公司 | Knowledge-graph-based industrial chain multi-cooperation intelligent decision method |
| CN117194764A (en) * | 2023-03-22 | 2023-12-08 | 山东浪潮爱购云链信息科技有限公司 | Goods display method, equipment and medium based on multi-platform fusion mall |
| CN117196763A (en) * | 2023-08-15 | 2023-12-08 | 华南农业大学 | Commodity sequence recommending method based on time sequence perception self-attention and contrast learning |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120179704A1 (en) * | 2009-09-16 | 2012-07-12 | Nanyang Technological University | Textual query based multimedia retrieval system |
| CN104978314B (en) * | 2014-04-01 | 2019-05-14 | 深圳市腾讯计算机系统有限公司 | Media content recommendations method and device |
| US11354747B2 (en) * | 2016-04-16 | 2022-06-07 | Overbond Ltd. | Real-time predictive analytics engine |
-
2024
- 2024-01-08 CN CN202410023026.1A patent/CN117520864B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012078768A (en) * | 2010-09-06 | 2012-04-19 | Nippon Telegr & Teleph Corp <Ntt> | Person matching device, method and program |
| CN109255651A (en) * | 2018-08-22 | 2019-01-22 | 重庆邮电大学 | A kind of search advertisements conversion intelligent Forecasting based on big data |
| CN112631560A (en) * | 2020-12-29 | 2021-04-09 | 上海海事大学 | Method and terminal for constructing objective function of recommendation model |
| CN113537728A (en) * | 2021-06-24 | 2021-10-22 | 上海阿法析地数据科技有限公司 | Intelligent recommendation system and recommendation method based on business recruitment in industrial park |
| CN115170247A (en) * | 2022-08-03 | 2022-10-11 | 杭州么贝软件科技有限公司 | Intelligent matching recommendation method for commodities of e-commerce shopping platform |
| CN115422452A (en) * | 2022-08-30 | 2022-12-02 | 温州佳润科技发展有限公司 | Smart home control method, device, equipment and storage medium based on big data |
| CN115391669A (en) * | 2022-10-31 | 2022-11-25 | 江西渊薮信息科技有限公司 | Intelligent recommendation method and device and electronic equipment |
| CN116596564A (en) * | 2023-02-21 | 2023-08-15 | 重庆协洽科技有限公司 | Method based on customer preference product adaptation technology |
| CN116402524A (en) * | 2023-02-22 | 2023-07-07 | 扬州市职业大学(扬州开放大学) | Video software user payment preference and influence factor analysis system thereof |
| CN117194764A (en) * | 2023-03-22 | 2023-12-08 | 山东浪潮爱购云链信息科技有限公司 | Goods display method, equipment and medium based on multi-platform fusion mall |
| CN116523597A (en) * | 2023-05-02 | 2023-08-01 | 肖刚 | E-commerce customization recommendation method for big data cloud entropy mining |
| CN116680320A (en) * | 2023-06-13 | 2023-09-01 | 张琼琼 | Mixed matching method based on big data |
| CN116739794A (en) * | 2023-08-10 | 2023-09-12 | 北京中关村银行股份有限公司 | User personalized scheme recommendation method and system based on big data and machine learning |
| CN117196763A (en) * | 2023-08-15 | 2023-12-08 | 华南农业大学 | Commodity sequence recommending method based on time sequence perception self-attention and contrast learning |
| CN117172725A (en) * | 2023-08-28 | 2023-12-05 | 合肥人工智能与大数据研究院有限公司 | Knowledge-graph-based industrial chain multi-cooperation intelligent decision method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117520864A (en) | 2024-02-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106651546B (en) | Electronic commerce information recommendation method oriented to smart community | |
| US11367086B2 (en) | System and method for an estimated consumer price | |
| CN106844787A (en) | It is a kind of for automobile industry finds targeted customer and matches the recommendation method of target product | |
| JP2016522523A (en) | Method and system for recommending information | |
| CN111666424A (en) | Steam part inquiry and quotation optimization method based on knowledge representation learning | |
| Zhang et al. | Improving the Bass model’s predictive power through online reviews, search traffic and macroeconomic data | |
| WO2022081267A1 (en) | Product evaluation system and method of use | |
| CN111966886A (en) | Object recommendation method, object recommendation device, electronic equipment and storage medium | |
| US20130246184A1 (en) | Method and system for displaying a contextual advertisement on a webpage | |
| Sarkar et al. | Optimizing e-commerce profits: A comprehensive machine learning framework for dynamic pricing and predicting online purchases | |
| CN112541111A (en) | Commodity retrieval and commodity recommendation system based on decentralized big data retrieval market | |
| CN111429214A (en) | Transaction data-based buyer and seller matching method and device | |
| JP6709775B2 (en) | Calculation device, calculation method, and calculation program | |
| CN117520864B (en) | Multi-feature fusion intelligent matching method for data elements | |
| CN117633219A (en) | Complaint classification method, device, equipment and storage medium | |
| CN110490682A (en) | The method and apparatus for analyzing item property | |
| CN113283960B (en) | Vertical e-commerce platform commodity intelligent recommendation method based on big data analysis and cloud computing and cloud service platform | |
| Hung | Using Cloud Services to Develop Marketing Information System Applications | |
| CN113269610A (en) | Bank product recommendation method and device and storage medium | |
| CN115169337B (en) | Method for calculating keyword score in commodity title optimization | |
| CN116911913B (en) | Method and device for predicting interaction result | |
| US20230169540A1 (en) | Systems and methods of providing enhanced contextual intelligent information | |
| Adiningtyas et al. | Customer perceived value: a study based on customer perception on social media | |
| Hung | Customized products and cloud service information system development research | |
| Sariyeva | Development and Research Of Classification Models On Base Of “Decision Tree” method for E-Commerce Systems |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |